Zhiyong Cui

I am a PhD Candidate in the Smart Transportation Application and Research Lab (STAR Lab) in the Department of Civil & Environmental Engineering at University of Washington advised by Prof. Yinhai Wang. I received my Master degree in Software Engineering from Peking University advised by Dr. Ying Huang and Prof. Tong Mo and earned a Bachelor degree in Software Engineering from Beihang University. During my Master study, I worked as a visiting student in the College of Electrical Engineering and Computer Science at National Taiwan University advised by Prof. Hsin-Mu (Michael) Tsai.

Research Focus

  • Deep Learning Modeling and Applications in Transportation, including Graph Convolution Neural Network (NN), recurrent NN, Generative Adversarial Network, etc.
  • Traffic Prediction, Traffic Network Modeling, Tarffic Data Imputation, etc.
  • Spatiotemporal Data Analysis, Geospatial Map Conflation, Transportation Data Platforms, etc.

Selected Research on Deep Learning based Traffic Prediction and Data Imputation

  1. Cui, Z., Henrickson, K., Ke, R., & Wang, Y.* (2019). Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting. (submitted to IEEE Transaction on Intelligent Transportation Systems; under review). [arXiv][code][data]
  1. Cui, Z., Ke, R., & Wang, Y.* (2018). Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction. (submitted to IEEE Transaction on Intelligent Transportation Systems; under review). [arXiv][code][data]

  2. Liang, Y., Cui, Z., Tian, Y., Chen, H., & Wang, Y.* (2018). A Deep Generative Adversarial Architecture for Network-Wide Spatial-Temporal Traffic State Estimation. Transportation Research Record. [arXiv]

Selected Research on Geospatial Transportation Data Integration

  1. Cui, Z., Henrickson, K., Pu, Z., Guo, G., & Wang, Y.* (2019). A New Multi-Source Traffic Data Integration Framework for Traffic Analysis and Performance Measurement. Transportation Research Board 98th Annual Meeting. [slides]